Yi-Shan Wu

Thanks:

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

RLHF & Preference Learning (1)Training Efficiency & Optimization (1)World Models & Planning (1)

Papers (1)

Aug 20, 2026

Thanks:1w ago

Time-Uniform Self-Normalized Concentration for Discounted Least Squares: Limits and Corrections

A simple Gaussian counterexample reveals that existing concentration inequalities for discounted least-squares estimators are fundamentally flawed, necessitating significant corrections.

Yi-Shan Wu

RLHF & Preference Learning Training Efficiency & Optimization World Models & Planning

Search

Yi-Shan Wu

Publication activitypapers/week, last 8 weeks

Research focus

Papers (1)